
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')


df = pd.read_csv(r"F:\data_set\netflix_dataset.csv")


df.head(5)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8807 entries, 0 to 8806
Data columns (total 12 columns):
 #   Column        Non-Null Count  Dtype 
---  ------        --------------  ----- 
 0   show_id       8807 non-null   object
 1   type          8807 non-null   object
 2   title         8807 non-null   object
 3   director      6173 non-null   object
 4   cast          7982 non-null   object
 5   country       7976 non-null   object
 6   date_added    8797 non-null   object
 7   release_year  8807 non-null   int64 
 8   rating        8803 non-null   object
 9   duration      8804 non-null   object
 10  listed_in     8807 non-null   object
 11  description   8807 non-null   object
dtypes: int64(1), object(11)
memory usage: 825.8+ KB


df.isna().sum().sum()

4307


df.loc[[3]].isna().sum().sum()

3


 df.dropna(axis=1, how='all')


df.dropna(axis=1, how='any')


def fun(df): 
    return df.fillna(1, inplace=True)


df.shape

(8807, 12)


df.rename(columns={"listed_in": "genre"},inplace=True)
df.head(5)


df["show_id"]=df["show_id"].apply(lambda x: x.replace("s",""))
df.head(5)


df.describe(include="object").T


plt.title("Percentage of Movies vs TV Shows available on Netflix as of 2021")
df['type'].value_counts().plot(kind = "pie", autopct="%.2f")
circle = plt.Circle((0, 0), 0.38, color='white')
plt.gcf().gca().add_artist(circle)
plt.show()


df["director"].value_counts().head(10)

Rajiv Chilaka             19
Raúl Campos, Jan Suter    18
Marcus Raboy              16
Suhas Kadav               16
Jay Karas                 14
Cathy Garcia-Molina       13
Martin Scorsese           12
Youssef Chahine           12
Jay Chapman               12
Steven Spielberg          11
Name: director, dtype: int64


df_dir=df[["title","director"]]
df_dir["director"]=df_dir["director"].str.split(", ")
df_dir= df_dir.explode("director")


df_dir["director"].value_counts().head(10)

Rajiv Chilaka          22
Jan Suter              21
Raúl Campos            19
Suhas Kadav            16
Marcus Raboy           16
Jay Karas              15
Cathy Garcia-Molina    13
Jay Chapman            12
Youssef Chahine        12
Martin Scorsese        12
Name: director, dtype: int64


sns.set_theme(style="whitegrid")
sns.set(rc={"axes.facecolor":"lightgrey"})
plt.figure(figsize= (10,6))
sns.countplot(palette="icefire",y=df_dir["director"],order=pd.value_counts(df_dir["director"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 director ")
plt.show()


df_actor=df[["title","cast"]]
df_actor["cast"]=df_actor["cast"].str.split(",")
df_actor= df_actor.explode("cast")


sns.set_theme(style="whitegrid")
sns.set(rc={"axes.facecolor":"lightgrey"})
plt.figure(figsize= (10,6))
sns.countplot(palette="mako",y=df_actor["cast"],order=pd.value_counts(df_actor["cast"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 Actors ")
plt.show()


df_country=df[["country"]]
df_country["country"]=df_country["country"].str.split(", ")
df_country= df_country.explode("country")


df_country["country"].value_counts().head(10)

United States     3689
India             1046
United Kingdom     804
Canada             445
France             393
Japan              318
Spain              232
South Korea        231
Germany            226
Mexico             169
Name: country, dtype: int64


sns.set_theme(style="whitegrid")
sns.set(rc={"axes.facecolor":"lightgrey"})
plt.figure(figsize= (10,6))
sns.countplot(palette="mako",x=df["country"],hue=df["type"],order=pd.value_counts(df_country["country"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 Country Based Number Content")
plt.show()


total_count = df["title"].value_counts().sum()
top_10 = df_country["country"].value_counts().head(10).sum()
print(round((top_10/total_count)*100,2),"%")

85.76 %


total_count = df["title"].value_counts().sum()
top_10 = df_country["country"].value_counts().head(5).sum()
print(round((top_10/total_count)*100,2),"%")

72.41 %


total_count = df["title"].value_counts().sum()
top_10 = df_country["country"].value_counts().head(1).sum()
print(round((top_10/total_count)*100,2),"%")

41.89 %


df_genre=df[["genre"]]
df_genre["genre"]=df_genre["genre"].str.split(", ")
df_genre= df_genre.explode("genre")


df_genre["genre"].value_counts().head(10)

International Movies        2752
Dramas                      2427
Comedies                    1674
International TV Shows      1351
Documentaries                869
Action & Adventure           859
TV Dramas                    763
Independent Movies           756
Children & Family Movies     641
Romantic Movies              616
Name: genre, dtype: int64


sns.set_theme(style="whitegrid")
sns.set(rc={"axes.facecolor":"lightgrey"})
sns.countplot(palette="magma",y=df_genre["genre"],order=pd.value_counts(df_genre["genre"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 genre")
plt.show()


df["release_year"].value_counts().head(10)

2018    1147
2017    1032
2019    1030
2020     953
2016     902
2021     592
2015     560
2014     352
2013     288
2012     237
Name: release_year, dtype: int64


year_wise =pd.value_counts(df["release_year"]).reset_index().head(30)
year_wise.rename(columns={"index":"year_of_release","release_year":"No_of_movies_and_tv_shows"},inplace=True)


sns.set_theme(style="whitegrid")
sns.set(rc={"axes.facecolor":"lightgrey"})
plt.figure(figsize=(10,8))
sns.barplot(data=year_wise,x="year_of_release",y="No_of_movies_and_tv_shows")
plt.xticks(rotation=90 ,fontsize=10)
plt.title("Movies and T.V shows Released Year Wise")
plt.show()


year_wise = pd.value_counts(df["release_year"]).reset_index().head(30)
year_wise.rename(columns={"index":"Year of release","release_year":"No. of titles"}, inplace = True)

df_mov_tv_rel = df[['type', 'release_year']]

df_mov_tv_rel = df_mov_tv_rel.value_counts().reset_index()
df_mov_tv_rel.rename(columns  = {0: 'count'}, inplace = True)

df_mov_tv_rel = df_mov_tv_rel[df_mov_tv_rel["release_year"]>=1992]

plt.figure(figsize = (10, 6))
a = sns.lineplot(data=df_mov_tv_rel, x="release_year", y="count", legend='auto', palette = 'viridis',hue ='type',linewidth = 2, marker = 'o')
for i, j in zip(df_mov_tv_rel["release_year"], df_mov_tv_rel["count"]):
    a.text(i, j, str(j), fontsize = 10) 
plt.title("Year wise count of content release (1992 - 2021)")
a.set_ylabel('Release count')
a.set_xlabel('Release Year')
plt.show()


Month = df[["date_added"]].replace(np.nan,"No_date")
Month["Release_month"] = Month["date_added"].apply(lambda x:x.lstrip().split(" ")[0])


Month["Release_month"].value_counts().head(12)

July         827
December     813
September    770
April        764
October      760
August       755
March        742
January      738
June         728
November     705
May          632
February     563
Name: Release_month, dtype: int64


sns.set_theme(style="whitegrid")
sns.set(rc={"axes.facecolor":"lightgrey"})
sns.countplot(palette="rainbow",y= Month["Release_month"],order=pd.value_counts(Month["Release_month"]).head(12).index)
plt.xticks(fontsize=10)
plt.title("Month wise Content added")
plt.show()


sns.set_theme(style="whitegrid")
plt.figure(figsize=(10,8))
sns.set(rc={"axes.facecolor":"lightgrey"})
sns.countplot(palette="rainbow",x= Month["Release_month"],hue=df["type"],order=pd.value_counts(Month["Release_month"]).head(12).index)
plt.xticks(rotation = 45,fontsize=10)
plt.title("Month Wise Content added")
plt.show()


df["rating"].value_counts()[:-3]

TV-MA       3207
TV-14       2160
TV-PG        863
R            799
PG-13        490
TV-Y7        334
TV-Y         307
PG           287
TV-G         220
NR            80
G             41
TV-Y7-FV       6
NC-17          3
UR             3
Name: rating, dtype: int64


sns.set_theme(style="whitegrid")
plt.figure(figsize=(10,8))
sns.countplot(palette="magma",x=df["rating"],hue=df["type"],order=pd.value_counts(df["rating"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top Rating Based on No. Of Content")
plt.show()


movies_df=df.loc[(df["type"]=="Movie")]
movies_df.reset_index()
movies_df.columns.name=None


df_movie_dir=movies_df[["director"]]
df_movie_dir["director"]=df_movie_dir["director"].str.split(", ")
df_movie_dir= df_movie_dir.explode("director")


sns.set_theme(style="whitegrid")
sns.countplot(palette="viridis",y=df_movie_dir["director"],order=pd.value_counts(df_movie_dir["director"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 Movies Directors")
plt.show()


df_movie_cast=movies_df[["cast"]]
df_movie_cast["cast"]=df_movie_cast["cast"].str.split(", ")
df_movie_cast= df_movie_cast.explode("cast")


sns.set_theme(style="whitegrid")
sns.countplot(palette="rainbow",y=df_movie_cast["cast"],order=pd.value_counts(df_movie_cast["cast"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 Movies Actors")
plt.show()


movies_df['duration'] = movies_df['duration'].astype(str).str.replace(' min', '')
movies_df.head(5)


movies_df.dropna(subset=["duration"],axis=0,inplace=True)


movies_df["duration"]=movies_df["duration"].astype(float)


movies_df["duration"].describe()

count    6128.000000
mean       99.577187
std        28.290593
min         3.000000
25%        87.000000
50%        98.000000
75%       114.000000
max       312.000000
Name: duration, dtype: float64


sns.boxplot(movies_df['duration'])
plt.show()


df_movie_genre=movies_df[["genre"]]
df_movie_genre["genre"]=df_movie_genre["genre"].str.split(", ")
df_movie_genre= df_movie_genre.explode("genre")


sns.set_theme(style="whitegrid")
sns.countplot(palette="rainbow",y=df_movie_genre["genre"],order=pd.value_counts(df_movie_genre["genre"]).head(10).index)
plt.xticks( fontsize=10)
plt.title("Top 10 Movies Genre")
plt.show()


tv_show_df=df.loc[(df["type"]=="TV Show")]
tv_show_df.reset_index()
tv_show_df.columns.name=None


tv_show_df.head(5)


tv_show_df['duration'].astype(str)

1       2 Seasons
2        1 Season
3        1 Season
4       2 Seasons
5        1 Season
          ...    
8795    2 Seasons
8796    2 Seasons
8797    3 Seasons
8800     1 Season
8803    2 Seasons
Name: duration, Length: 2676, dtype: object


sns.set_theme(style="whitegrid")
ax=sns.countplot(palette="magma",x=tv_show_df['duration'],order=pd.value_counts(tv_show_df['duration']).index)
plt.xticks(rotation = 90)
for p in ax.patches:
        ax.annotate(str(p.get_height()), (p.get_x() * 1.005, (p.get_height() * 1.005)))
plt.title("TV Shows duration ")
plt.show()


df_tv_dir=tv_show_df[["director"]]
df_tv_dir["director"]=df_tv_dir["director"].str.split(", ")
df_tv_dir= df_tv_dir.explode("director")


sns.set_theme(style="whitegrid")
sns.countplot(palette="rocket",y=df_tv_dir["director"],order=pd.value_counts(df_tv_dir["director"]).head(10).index)
plt.xticks(rotation=90, fontsize=10)
plt.title("Top 10 TV Show Directors")
plt.show()


df_tv_cast=tv_show_df[["cast"]]
df_tv_cast["cast"]=df_tv_cast["cast"].str.split(", ")
df_tv_cast= df_tv_cast.explode("cast")


sns.set_theme(style="whitegrid")
sns.countplot(palette="mako",y=df_tv_cast["cast"],order=pd.value_counts(df_tv_cast["cast"]).head(10).index)
plt.xticks(rotation=90, fontsize=10)
plt.title("Top 10 TV Show Actors")
plt.show()


df_tv_genre=tv_show_df[["genre"]]
df_tv_genre["genre"]=df_tv_genre["genre"].str.split(", ")
df_tv_genre= df_tv_genre.explode("genre")


sns.set_theme(style="whitegrid")
sns.countplot(palette="mako",y=df_tv_genre["genre"],order=pd.value_counts(df_tv_genre["genre"]).head(10).index)
plt.xticks(rotation=90, fontsize=10)
plt.title("Top 10 TV Show Genre")
plt.show()


Date = df[['date_added']].dropna()
Date['date'] = Date['date_added'].apply(lambda x : x.lstrip().split(' ')[1].replace(",",""))
Date['months'] = Date['date_added'].apply(lambda x : x.lstrip().split(' ')[0])
Date['years'] = Date['date_added'].apply(lambda x : x.split(', ')[-1])
Order_Of_Month = ['January', 'February', 'March', 'April', 'May','June', 'July', 'August', 'September', 'October', 'November','December'][::-1]
df8 = Date.groupby('years')['months'].value_counts().unstack().fillna(0)[Order_Of_Month].T[::-1]


Date['date'].value_counts().sort_values(ascending=False).reset_index().head()


perc_1 = (Date['date'].value_counts()[30]/Date['date'].value_counts().sum())*100
print((round(perc_1,2)),"%")

1.6 %


plt.figure(figsize=(8,6))
sns.distplot(Date['date'])
plt.title('KDE plot for the day wise Content added')
plt.show()


Date = df[['date_added']].dropna()
Date['months'] = Date['date_added'].apply(lambda x : x.lstrip().split(' ')[0])
Date['years'] = Date['date_added'].apply(lambda x : x.split(', ')[-1])
Order_Of_Month = ['January', 'February', 'March', 'April', 'May','June', 'July', 'August', 'September', 'October', 'November','December'][::-1]
df8 = Date.groupby('years')['months'].value_counts().unstack().fillna(0)[Order_Of_Month].T[::-1]


plt.figure(figsize=(17,8))
sns.heatmap(data=df8,annot=True,linewidth=0.5,fmt=".0f",cmap="crest")
plt.title('Frequency Of Content Updated on Netflix', fontsize=20,fontfamily='Arial', fontweight='bold')
plt.show()


df.dropna(subset=["duration", "rating", "date_added"], inplace = True)


round((df.isnull().sum()/df.shape[0]*100),2).sort_values(ascending = False)

director        29.82
country          9.43
cast             9.39
show_id          0.00
type             0.00
title            0.00
date_added       0.00
release_year     0.00
rating           0.00
duration         0.00
genre            0.00
description      0.00
dtype: float64


# Replacing NaN values in cast column with "No Cast"

df["cast"].replace(np.NaN, "No Cast", inplace = True)


# Replacing NaN values in country column with "Unknown"

df["country"].replace(np.NaN, "Unknown", inplace = True)


round((df.isna().sum()/df.shape[0]*100),2).sort_values(ascending = False)

director        29.82
show_id          0.00
type             0.00
title            0.00
cast             0.00
country          0.00
date_added       0.00
release_year     0.00
rating           0.00
duration         0.00
genre            0.00
description      0.00
dtype: float64

	show_id	type	title	release_year	listed_in	description
0	s1	Movie	Dick Johnson Is Dead	2020	Documentaries	As her father nears the end of his life, filmm...
1	s2	TV Show	Blood & Water	2021	International TV Shows, TV Dramas, TV Mysteries	After crossing paths at a party, a Cape Town t...
2	s3	TV Show	Ganglands	2021	Crime TV Shows, International TV Shows, TV Act...	To protect his family from a powerful drug lor...
3	s4	TV Show	Jailbirds New Orleans	2021	Docuseries, Reality TV	Feuds, flirtations and toilet talk go down amo...
4	s5	TV Show	Kota Factory	2021	International TV Shows, Romantic TV Shows, TV ...	In a city of coaching centers known to train I...
...	...	...	...	...	...	...
8802	s8803	Movie	Zodiac	2007	Cult Movies, Dramas, Thrillers	A political cartoonist, a crime reporter and a...
8803	s8804	TV Show	Zombie Dumb	2018	Kids' TV, Korean TV Shows, TV Comedies	While living alone in a spooky town, a young g...
8804	s8805	Movie	Zombieland	2009	Comedies, Horror Movies	Looking to survive in a world taken over by zo...
8805	s8806	Movie	Zoom	2006	Children & Family Movies, Comedies	Dragged from civilian life, a former superhero...
8806	s8807	Movie	Zubaan	2015	Dramas, International Movies, Music & Musicals	A scrappy but poor boy worms his way into a ty...

	show_id	type	title	director	cast	country	date_added	release_year	rating	duration	listed_in	description
0	s1	Movie	Dick Johnson Is Dead	Kirsten Johnson	NaN	United States	September 25, 2021	2020	PG-13	90 min	Documentaries	As her father nears the end of his life, filmm...
1	s2	TV Show	Blood & Water	NaN	Ama Qamata, Khosi Ngema, Gail Mabalane, Thaban...	South Africa	September 24, 2021	2021	TV-MA	2 Seasons	International TV Shows, TV Dramas, TV Mysteries	After crossing paths at a party, a Cape Town t...
2	s3	TV Show	Ganglands	Julien Leclercq	Sami Bouajila, Tracy Gotoas, Samuel Jouy, Nabi...	NaN	September 24, 2021	2021	TV-MA	1 Season	Crime TV Shows, International TV Shows, TV Act...	To protect his family from a powerful drug lor...
3	s4	TV Show	Jailbirds New Orleans	NaN	NaN	NaN	September 24, 2021	2021	TV-MA	1 Season	Docuseries, Reality TV	Feuds, flirtations and toilet talk go down amo...
4	s5	TV Show	Kota Factory	NaN	Mayur More, Jitendra Kumar, Ranjan Raj, Alam K...	India	September 24, 2021	2021	TV-MA	2 Seasons	International TV Shows, Romantic TV Shows, TV ...	In a city of coaching centers known to train I...

	count	unique	top	freq
show_id	8807	8807	1	1
type	8807	2	Movie	6131
title	8807	8807	Dick Johnson Is Dead	1
director	6173	4528	Rajiv Chilaka	19
cast	7982	7692	David Attenborough	19
country	7976	748	United States	2818
date_added	8797	1767	January 1, 2020	109
rating	8803	17	TV-MA	3207
duration	8804	220	1 Season	1793
genre	8807	514	Dramas, International Movies	362
description	8807	8775	Paranormal activity at a lush, abandoned prope...	4

	index	date
0	1	2212
1	15	687
2	2	325
3	16	289
4	31	274

1.Defining Problem Statement¶

Importing libraries¶

Loading Dataset¶

1. Defining Problem Statement and Analysing basic metrics¶

Exploratory Data Analysis¶

Non-Graphical Analysis: Value Counts and Unique attributes¶

1.Shape of the Data¶

2.Rename the "listed_in" into genre¶

3. Removing "S" from show_id¶

4. Describing the String values¶

Movies vs TV Shows¶

Before Un-nesting the "Director" column¶

After un-nesting the "Director" columns¶

Top 10 directors¶

Top 10 Actors¶

Top 10 Countries Content¶

Percentage Contribution Top 10 Countries to the total content of Netfix¶

Percentage Contribution Top 5 Countries to the total content of Netfix¶

Percentage Contribution Top 1 Countries to the total content of Netfix¶

Top 10 Genres¶

Content Released Year wise¶

Movies and TV shows Released Year Wise¶

Content Added To Netflix Month Wise¶

Month Wise Movies and TV Show added to Netflix¶

Ratings According to the Movies and TV Show¶

Movies Vs Tv show¶

Netflix_Movies¶

Top 10 Movies Directors¶

Top 10 Movies Movies Actors¶

Movies Duration in Boxplot¶

Top 10 Movies Movies Genre¶

Netfix_Tv_shows¶

Top TV Shows Directors¶

Days on Which Content is added Every Month¶

Correlation of the Year and Months of the content added¶

5. MISSING VALUE TREATMENT (Dropping Null Values)¶

Insights based on Non-Graphical and Visual Analysis¶

Business Insights¶

Recommendations¶

1. Which countries to target?¶

3. Average duration of the Movie/TV shows?¶

4. In which month to add a Movie/TV show?¶

5. Which directors can be preferred for Movies/TV Shows?¶

6. Which actors can be considered Movies/TV Shows?¶

7. When to add new content?¶

8. Which rating to consider?¶

Additional point to be considered:¶